© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65659
    Prev
    Next
    INDEX
    Explanations

    Rosewood, Tyrosine, question start

    np_acts-logits-general · gemini-2.5-flash-lite

    line breaks and whitespace in code or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ///<
    -1.38
    %;
    
    -1.14
    //=
    -1.08
    //!
    -1.06
     område
    -1.04
     Tienes
    -1.02
     във
    -1.02
    //{
    -1.01
    ''')
    -1.01
     préférable
    -1.00
    POSITIVE LOGITS
    const
    1.38
     and
    1.15
     const
    1.11
     cabrio
    1.09
     riviera
    1.05
     sven
    1.03
     the
    1.02
     also
    1.00
     often
    0.98
     sometimes
    0.97
    Activations Density 0.008%

    No Known Activations